🔍 feat: Web Search via OpenAI Responses API (#8186)

* 🔍 feat: Introduce Web Search Functionality for OpenAI API

- Added a new web_search parameter to enable web search capabilities in the OpenAI configuration.
- Updated the DynamicSlider component for improved styling.
- Enhanced the useSetIndexOptions hook to auto-enable the Responses API when web search is activated.
- Modified relevant schemas, types, and translation files to support the new web search feature.

* chore: remove comments

* refactor: tool handling in initializeAgent for better clarity and functionality and reflection of openai features

---------

Co-authored-by: Danny Avila <danny@librechat.ai>

client/src/components/SidePanel/Parameters/DynamicSlider.tsx

@@ -197,7 +197,7 @@ function DynamicSlider({
                   defaultTextProps,
                   cn(
                     optionText,
-                    'reset-rc-number-input reset-rc-number-input-text-right h-auto w-12 border-0 py-1 text-xs group-hover/temp:border-gray-200',
+                    'reset-rc-number-input h-auto w-14 border-0 py-1 pl-1 text-center text-xs group-hover/temp:border-gray-200',
                   ),
                 )}
               />

client/src/hooks/Conversations/useSetIndexOptions.ts

@@ -30,6 +30,14 @@ const useSetIndexOptions: TUseSetOptions = (preset = false) => {
       };
     }
 
+    // Auto-enable Responses API when web search is enabled
+    if (param === 'web_search' && newValue === true) {
+      const currentUseResponsesApi = conversation?.useResponsesApi ?? false;
+      if (!currentUseResponsesApi) {
+        update['useResponsesApi'] = true;
+      }
+    }
+
     setConversation(
       (prevState) =>
         tConvoUpdateSchema.parse({

client/src/locales/en/translation.json

@@ -234,6 +234,7 @@
   "com_endpoint_openai_temp": "Higher values = more random, while lower values = more focused and deterministic. We recommend altering this or Top P but not both.",
   "com_endpoint_openai_topp": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We recommend altering this or temperature but not both.",
   "com_endpoint_openai_use_responses_api": "Use the Responses API instead of Chat Completions, which includes extended features from OpenAI. Required for o1-pro, o3-pro, and to enable reasoning summaries.",
+  "com_endpoint_openai_use_web_search": "Enable web search functionality using OpenAI's built-in search capabilities. This allows the model to search the web for up-to-date information and provide more accurate, current responses.",
   "com_endpoint_output": "Output",
   "com_endpoint_plug_image_detail": "Image Detail",
   "com_endpoint_plug_resend_files": "Resend Files",